© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177581
    Prev
    Next
    INDEX
    Explanations

    main districts

    np_acts-logits-general · gemini-2.5-flash-lite

    divine text project console constantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    歟
    0.51
    డాది
    0.50
     جري
    0.50
     कार्यवाही
    0.48
    ப்பர்
    0.47
     povas
    0.46
     ছিলোনা
    0.46
     thom
    0.45
     دونك
    0.45
    க்களை
    0.44
    POSITIVE LOGITS
    ln
    0.50
    lng
    0.49
    瞠
    0.49
    льные
    0.48
    ll
    0.48
    tip
    0.47
     portrayed
    0.47
    级
    0.46
     pulverized
    0.45
    glied
    0.45
    Activations Density 0.000%

    No Known Activations